# On regroupe selon les modalites de la DrivAge
# l'exposition, le nombre de sinistres et la frequence
-df_plot <- dat %>%
- group_by(DrivAge) %>%
+df_plot <- dat |>
+ group_by(DrivAge) |>
summarize(
exp = sum(Exposure),
nb_claims = sum(ClaimNb),
@@ -5049,20 +5049,20 @@ package ggplot2.
)
# Histogramme exposition
-p1 <- ggplot(df_plot, aes(x = DrivAge, y = exp)) +
+p1 <- ggplot(df_plot, aes(x = DrivAge, y = exp)) +
geom_bar(stat = "identity", fill = "grey", color = "black", alpha = 0.5) +
labs(x = "Age du conducteur", y = "Exposition en années") +
theme_bw()
- # Histogramme frequence
- p2 <- ggplot(df_plot, aes(x = DrivAge, y = freq)) +
- geom_bar(stat = "identity", fill = "grey", color = "black", alpha = 0.5) +
- labs(x = "Age du conducteur", y = "Frequence") +
- theme_bw()
-
-plot_grid(p1, p2, labels = c('A', 'B'), label_size = 12)df_plot <- dat %>%
- group_by(DrivAge) %>%
+# Histogramme frequence
+p2 <- ggplot(df_plot, aes(x = DrivAge, y = freq)) +
+ geom_bar(stat = "identity", fill = "grey", color = "black", alpha = 0.5) +
+ labs(x = "Age du conducteur", y = "Frequence") +
+ theme_bw()
+
+plot_grid(p1, p2, labels = c("A", "B"), label_size = 12)df_plot <- dat |>
+ group_by(DrivAge) |>
summarize(
exp = sum(Exposure),
nb_claims = sum(ClaimNb),
@@ -5071,9 +5071,9 @@ package ggplot2.
# Scatter plot frequence
p3 <- ggplot(df_plot, aes(x = DrivAge, y = freq)) +
- geom_point() +
+ geom_point() +
geom_smooth() +
- labs(x = "Age du conducteur", y = "Frequence") +
+ labs(x = "Age du conducteur", y = "Frequence") +
theme_bw()
p3
DrivAge et BonusMalus.
# On regroupe selon les modalites de la DrivAge et de Area
-# l'exposition, le nombre de sinistres et la frequence
-df_plot <- dat %>%
- group_by(DrivAge, BonusMalus) %>%
+# l'exposition, le nombre de sinistres et la frequence
+df_plot <- dat |>
+ group_by(DrivAge, BonusMalus) |>
summarize(
exp = sum(Exposure),
nb_claims = sum(ClaimNb),
@@ -5097,7 +5097,7 @@ améliorations en modifiant les variables DrivAge et BonusMal
)
p4 <- ggplot(df_plot, aes(x = DrivAge, y = freq, color = BonusMalus)) +
- geom_point() +
+ geom_point() +
geom_smooth() +
labs(x = "Age du conducteur", y = "Frequence", color = "Bonus-Malus") +
theme_bw()
@@ -5115,29 +5115,31 @@ l’exposition est très faible.
lim_classes <- c(50, 75, 100, 125, Inf)
# Exclusion des donnees "extremes" et faire les regroupement
-df_plot <- dat %>%
- filter(DrivAge <= 85, BonusMalus <= 125) %>%
+df_plot <- dat |>
+ filter(DrivAge <= 85, BonusMalus <= 125) |>
# regroupement en classes d'ages de 5 ans
- mutate(DrivAge = ceiling(pmin(DrivAge, 85) / 5) * 5) %>%
- mutate(BonusMalus = cut(BonusMalus, breaks = lim_classes, include.lowest = TRUE))
-
-# On regroupe selon les modalites de la DrivAge et de Area
-# l'exposition, le nombre de sinistres et la frequence
-df_plot <- df_plot %>%
- group_by(DrivAge, BonusMalus) %>%
- summarize(
- exp = sum(Exposure),
- nb_claims = sum(ClaimNb),
- freq = sum(ClaimNb) / sum(Exposure)
- )
-
-# Scatter plot frequence
-p5 <- ggplot(df_plot, aes(x = DrivAge, y = freq, color = BonusMalus)) +
- geom_point() +
- geom_smooth() +
- labs(x = "Age du conducteur", y = "Frequence", color = "Bonus-Malus") +
- theme_bw()
-p5
@@ -5182,36 +5184,29 @@ couples.
# df : nom du data.frame
# var1 : nom de la variable explicative 1
# var2 : nom de la variable explicative 2
-plot_pairwise_disc <- function(df, var1, var2)
-{
- df <- rename(df, "varx" = all_of(var1), "vary" = all_of(var2))
-
-# replace variable vname by the binning variable
- if(is.numeric(df$varx))
- {
- df <- df %>%
- mutate(varx = ntile(varx, 5))
- }
-
- if(is.numeric(df$vary))
- {
- df <- df %>%
- mutate(vary = ntile(vary, 5),
- vary = factor(vary))
- }
-
- df %>%
- group_by(varx, vary) %>%
- summarize(exp = sum(Exposure),
- nb_claims = sum(ClaimNb),
- freq = sum(ClaimNb) / sum(Exposure), .groups = "drop") %>%
- ggplot(aes(x = varx,
- y = freq,
- colour = vary,
- group = vary), alpha = 0.3) +
- geom_point() + geom_line() + theme_bw() +
- labs(x = var1, y = "Frequence", colour = var2)
-}
+plot_pairwise_disc <- function(df, var1, var2) {
+ df <- rename(df, "varx" = all_of(var1), "vary" = all_of(var2))
+
+ # replace variable vname by the binning variable
+ if (is.numeric(df$varx)) {
+ df <- df |>
+ mutate(varx = ntile(varx, 5))
+ }
+
+ if (is.numeric(df$vary)) {
+ df <- df |>
+ mutate(vary = ntile(vary, 5), vary = factor(vary))
+ }
+
+ df |>
+ group_by(varx, vary) |>
+ summarize(exp = sum(Exposure),
+ nb_claims = sum(ClaimNb),
+ freq = sum(ClaimNb) / sum(Exposure), .groups = "drop") |>
+ ggplot(aes(x = varx, y = freq, colour = vary, group = vary), alpha = 0.3) +
+ geom_point() + geom_line() + theme_bw() +
+ labs(x = var1, y = "Frequence", colour = var2)
+}